# One attempt at a list of VM suites, one machine each. Called by _vm.yaml, which calls it up to three
# times: a hosted runner may land on a host with no KVM, and the host cannot be chosen, only drawn again.
#
# With `defer-no-kvm` a leg that lands on such a host does not fail: it uploads the artifact
# `kvm-missing-<run attempt>-<attempt>-<suite>` and succeeds without having run the suite, and the next
# attempt reads the artifacts to find the suites it has to run. The last attempt does not defer: a suite
# that found no KVM in every attempt fails.

name: vm-attempt

on:
  workflow_call:
    inputs:
      suites:
        description: The suites to run, as a JSON list (the first attempt); later attempts find theirs
        type: string
        default: "[]"
      attempt:
        description: 1, 2 or 3
        type: number
        required: true
      slow:
        description: The slow tier (the driver is run by hand, and its output kept), not the sandboxed `nix build`
        type: boolean
        default: false
      defer-no-kvm:
        type: boolean
        required: true

permissions:
  contents: read

jobs:
  # the suites that the attempt before found no KVM for
  plan:
    if: ${{ inputs.attempt > 1 }}
    runs-on: ubuntu-24.04
    timeout-minutes: 5
    permissions:
      actions: read
    outputs:
      suites: ${{ steps.plan.outputs.suites }}
    steps:
      - id: plan
        env:
          GH_TOKEN: ${{ github.token }}
          RUN_ATTEMPT: ${{ github.run_attempt }}
          ATTEMPT: ${{ inputs.attempt }}
        run: |
          # GitHub expressions cannot subtract: the attempt before is computed here
          PREFIX="kvm-missing-$RUN_ATTEMPT-$((ATTEMPT - 1))-"
          suites=$(gh api --paginate "repos/$GITHUB_REPOSITORY/actions/runs/$GITHUB_RUN_ID/artifacts" \
            --jq '.artifacts[].name' |
            jq -R --arg prefix "$PREFIX" 'select(startswith($prefix)) | ltrimstr($prefix)' |
            jq -sc .)
          echo "suites to run again: $suites"
          echo "suites=$suites" >> "$GITHUB_OUTPUT"

  suite:
    needs: [plan]
    if: ${{ !cancelled() && needs.plan.result != 'failure' && (inputs.attempt == 1 || needs.plan.outputs.suites != '[]') }}
    runs-on: ubuntu-24.04
    timeout-minutes: ${{ inputs.slow && 60 || 45 }}
    strategy:
      fail-fast: false
      max-parallel: 8
      matrix:
        suite: ${{ fromJson(inputs.attempt == 1 && inputs.suites || needs.plan.outputs.suites) }}
    steps:
      - uses: actions/checkout@v6
      - id: nix
        uses: ./.github/actions/nix
        with:
          kvm: "true"
          defer-no-kvm: ${{ inputs.defer-no-kvm }}
          cachix-cache: ${{ vars.CACHIX_CACHE }}
          cachix-auth-token: ${{ secrets.CACHIX_AUTH_TOKEN }}

      - name: Remember that this host had no KVM
        if: steps.nix.outputs.kvm == 'missing'
        run: echo "${{ matrix.suite }}" > kvm-missing
      - if: steps.nix.outputs.kvm == 'missing'
        uses: actions/upload-artifact@v7
        with:
          name: kvm-missing-${{ github.run_attempt }}-${{ inputs.attempt }}-${{ matrix.suite }}
          path: kvm-missing
          retention-days: 1

      # each suite in its own machine, in a sandboxed `nix build` like any other check
      - if: steps.nix.outputs.kvm == 'ready' && !inputs.slow
        run: nix build -L --no-link .#legacyPackages.x86_64-linux.vm.${{ matrix.suite }}

      # the driver is run by hand, outside the sandbox, so that the screenshots and the journals of a
      # failed run can be uploaded
      - if: steps.nix.outputs.kvm == 'ready' && inputs.slow
        run: nix build -L .#legacyPackages.x86_64-linux.vm.${{ matrix.suite }}.driver -o driver
      - if: steps.nix.outputs.kvm == 'ready' && inputs.slow
        run: mkdir -p out && cd out && ../driver/bin/nixos-test-driver -o .
      - if: ${{ always() && steps.nix.outputs.kvm == 'ready' && inputs.slow }}
        uses: actions/upload-artifact@v7
        with:
          name: ci-vm-${{ matrix.suite }}-${{ github.sha }}
          path: out/
          if-no-files-found: ignore
          retention-days: 7